DYNAMIC VISION
From Images to Face Recognition
by Shaogang Gong (Queen Mary and Westfield College) , Stephen J McKenna (University of Dundee) , & Alexandra Psarrou (University of Westminster)
Shaogang Gong is Reader in Computational Vision and Learning at Queen Mary and Westfield College, University of London, England. Dr Gong was born in 1964 in Chungking, China. He received his BSc (1985) in information theory and measurement from the University of Electronic Sciences and Technology of China and his DPhil (1989) in computer vision from Oxford University. He was a recipient of a Sino-Anglo Queen's Research Scientist Award in 1987, a Royal Society Research Fellow in 1987 and 1988, a GEC-Oxford Industrial Research Fellow in 1989, and a research fellow on the European ESPRIT II Project VIEWS between 1989–93. He has published over 80 articles in his areas of research interest currently including dynamic scene understanding, temporal prediction and motion-based recognition, face and gesture recognition, behaviour profiling and recognition, Bayesian and statistical models, visual learning, visual surveillance and visually mediated interaction.
Stephen McKenna is a Lecturer in Applied Computer Science at the University of Dundee, Scotland. Dr McKenna was born in 1969 and received his BSc (Hons) in Computer Science from the University of Edinburgh in 1990. He received his MSc (1993) and PhD (1994) in Computer Vision from the University of Dundee. He has been an EU HCM Research Fellow (Tecnopolis, Italy, 1994–95), a BT Research Fellow (BT Labs, England, 1996) and an invited visiting researcher at George Mason University (USA, 1999). Between 1995 and 1998 he was post-doctoral researcher in Computer Vision at Queen Mary and Westfield College, University of London. His research interests currently include dynamic vision, face recognition, machine learning, gesture-driven interfaces, perception of human action and supportive environments.
Alexandra Psarrou is Reader in Machine Vision at the University of Westminster, England. Dr Psarrou was born in 1963 in Athens, Greece and received her BSc (1987), MSc (1988) in Computer Science and PhD (1996) in Computer Vision from Queen Mary and Westfield College (QMW), London. She was a research fellow at QMW between 1990–1992. Her research interests include dynamic image understanding, modelling and prediction of motion using artificial neural networks, 2D and 3D shape indexing for content based search in image and video databases, modelling intelligent man-machine interfaces.
Face recognition is a task that the human vision system seems to perform almost effortlessly, yet the goal of building computer-based systems with comparable capabilities has proven to be difficult. The task implicitly requires the ability to locate and track faces through often complex and dynamic scenes. Recognition is difficult because of variations in factors such as lighting conditions, viewpoint, body movement and facial expression. Although evidence from psychophysical and neurobiological experiments provides intriguing insights into how we might code and recognise faces, its bearings on computational and engineering solutions are far from clear. The study of face recognition has had an almost unique impact on computer vision and machine learning research at large. It raises many challenging issues and provides a good vehicle for examining some difficult problems in vision and learning. Many of the issues raised are relevant to object recognition in general.
This book describes the latest models and algorithms that are capable of performing face recognition in a dynamic setting. The key question is how to design computer vision and machine learning algorithms that can operate robustly and quickly under poorly controlled and changing conditions. Consideration of face recognition as a problem in dynamic vision is perhaps both novel and important. The algorithms described have numerous potential applications in areas such as visual surveillance, verification, access control, video-conferencing, multimedia and visually mediated interaction.
The book will be of special interest to researchers and academics involved in machine vision, visual recognition and machine learning. It should also be of interest to industrial research scientists and managers keen to exploit this emerging technology and develop automated face and human recognition systems. It is also useful to postgraduate students studying computer science, electronic engineering, information or systems engineering, and cognitive psychology.
|
